{"total":17,"rows":[{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2405.20340","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","created":"2024-05-30","cited_by_count":90,"area":null},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2503.13139","title":"Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding","created":"2025-03-17","cited_by_count":34,"area":null},{"id":"2506.05904","title":"Proactive Assistant Dialogue Generation from Streaming Egocentric Videos","created":"2025-06-06","cited_by_count":28,"area":null},{"id":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2507.11245","title":"NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generation","created":"2025-07-15","cited_by_count":22,"area":null},{"id":"2402.13887","title":"Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models","created":"2024-02-21","cited_by_count":19,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12,"area":null},{"id":"2502.20480","title":"VideoA11y: Method and Dataset for Accessible Video Description","created":"2025-02-27","cited_by_count":9,"area":null},{"id":"2511.10953","title":"Language-Guided Graph Representation Learning for Video Summarization","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2502.12945","title":"LLMPopcorn: Exploring LLMs as Assistants for Popular Micro-video Generation","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2503.18637","title":"Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2509.11605","title":"DUAL-VAD: Dual Benchmarks and Anomaly-Focused Sampling for Video Anomaly Detection","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2503.00049","title":"Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2404.09633","title":"In-Context Translation: Towards Unifying Image Recognition, Processing, and Generation","created":"2024-04-15","cited_by_count":0,"area":null}],"next_cursor":null}